Microsoft Launches MAI-Transcribe-2-Streaming for Real-Time Transcriptions
Microsoft introduces MAI-Transcribe-2-Streaming, a streaming transcription model that tops Artificial Analysis's rankings.
Microsoft announced the launch of MAI-Transcribe-2-Streaming, a streaming transcription model that is the fastest, most accurate, and cheapest speech recognition model in the world. It is designed for real-time transcriptions and is available through various platforms including Microsoft Foundry, MAI Playground, and OpenRouter.
Key facts
| Fact | Detail | The source says |
|---|---|---|
| Model Name | MAI-Transcribe-2-Streaming | “MAI-Transcribe-2-Streaming” |
| Ranking | 1st on Artificial Analysis | “Our first streaming transcription model debuts at no. 1 on Artificial Analysis” |
| Characteristics | Fastest, most accurate, and cheapest | “MAI-Transcribe-2 is the fastest, most accurate and cheapest speech recognition model in the world” |
What happened
Microsoft has unveiled MAI-Transcribe-2-Streaming, a streaming transcription model that ranks at the top of Artificial Analysis's model rankings. According to the announcement, this model is the fastest, most accurate, and cheapest speech recognition model in the world. It is designed to provide real-time transcriptions and is available through Microsoft Foundry, MAI Playground, and OpenRouter. Additionally, Microsoft also introduced two new voice models, MAI-Voice-2.1 and MAI-Voice-2.1-Flash, which offer fast and fluid conversational experiences without compromising on accuracy or voice quality.
Source: Microsoft